All students following the course in the A.Y. 2023/2024 are requested to register in Google Classroom using the e-mail "@studenti.uniroma1.it". The registration code for the course is phjlu4f.

WARNING! The course is open to other students of the Faculty and of the University who are interested in the covered items, as there are NO preparatory or mandatory courses to be taken before.

Lectures will start on Wednesday the 27 of September and they will be held in the classroom IN PRESENCE ONLY ith the following time schedule:

• Wednesday, hr. 16:00-18:30, room 24, via Eudossiana n. 18, building RM031

• Thursday, hr. 17:00-18:30, room 40, via delle Sette Sale n. 12/B, building RM033  (accessed externally via DIAEE Department)

N.B.  There are shown actual times of lectures, bearing in mind that 15 minutes per hour are reserved for questions and discussions.

Office hours are scheduled by appointment and can be held either in person or remotely.

• Official site of the Master Degree in Industrial/Management Engineering

• Available Master's Theses

• Goals and learning outcomes

• Programme A.Y. 2023/2024. The final program of the course is referring to ALL and ONLY what was presented, explained and discussed during lectures (i.e., not including for this year the parts in red-colored text):

  • • • Introduction to Machine Learning. Basic concepts on supervised and unsupervised learning. Overview of machine learning and deep learning applications. 

      • Linear regression models. Least-squares estimation. Maximum Likelihood method. Shrinkage methods (ridge regression, LASSO, elastic net).

      • Model assessment and selection. Bias-variance decomposition. Generalization capability and generalization error. Overfitting and underfitting. Cross-validation and K-folding. Ockham's razor and early stopping. 

      • Nonlinear regression models. Polynomial models, kernel expansion, Bayesian models, neural networks, nonparametric methods.

      • Unsupervised learning. Clustering algorithms and cluster validity methods.

      • Classification methods. Linear classifiers, logistic regression, Linear Discriminant Analysis, Quadratic Discriminant Analysis, nonparametric methods (KNN).

      • Fundamentals of time series prediction.

      • Shallow neural networks. Radial Basis Function (RBF), Fuzzy Inference System (FIS) and ANFIS neurofuzzy networks, Extreme Learning Machine (ELM) and Random Vector Functional-Link (RVFL), Echo State Network (ESN). Basic concepts on randomization.

      • Deep neural networks. Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), Graph Neural Network (GNN).

      • Distributed learning and optimization techniques. Topology and networks of agents (smart sensors and actuators). Distributed Average Consensus (DAC), ADMM, heuristic algorithms. Distributed clustering and distributed classification. Distributed learning in recurrent and stacked deep networks.

      • Fundamentals of hyperdimensional computing.

      • Fundamentals of quantum computing. Quantum gates and quantum gate arrays. Quantum algorithms for optimization and information processing (QFFT, Grover, Schor). Quantum machine learning. Quantum neural networks.

      • Hands-on practices using Python and Matlab:

        • • linear regression, overfitting and underfitting;

          • classification and clustering;

          • deep learning;

          • graph neural networks;

          • quantum computing and quantum deep learning;

          • energy time series prediction; 

          • behavioral analysis.

      • Applications and case studies:

        • • prediction of renewable energy sources, intelligent energy systems, smart grids;

          • applications to real-world data (logistic, economic, biomedical, mechatronic, environmental, aerospace, etc.);

          • behavioral analysis and biometrics;

          • analysis of materials and industrial processes;

          • machine learning for the IoT/IoE, cooperative and competitive multi-agent learning, smart sensor networks;

          • federated and distributed learning systems;

          • quantum neural networks, quantum optimization, and quantum generative models. 

  • Exams Timetable A.Y. 2023/2024. Exams may be taken by appointment when it is deemed most appropriate starting from January 2022; the exam registration will take place in the official time windows provided by the Faculty calendar, as shown below:

    • • 1st round: January 2024

      • 2nd round: February 2024

      • Extra round: March/April 2024
        NOTE. Reserved to the categories of students indicated in the art. 40, par. 6 of the General Manifest of Studies ("Manifesto Generale degli Studi") of the University "La Sapienza". NO EXCEPTIONS ARE GRANTED.

      • 3rd round: June 2024

      • 4th round: July 2024

      • 5th round: September 2024

      • Extra round: October/November 2024
        NOTE. Reserved to the categories of students indicated in the art. 40, par. 6 of the General Manifest of Studies ("Manifesto Generale degli Studi") of the University "La Sapienza" , as well as to failing students and to students enrolled for A.Y. 2023/2024 in the 2nd year of the Master Degree. NO EXCEPTIONS ARE GRANTED.

  • References:

    • • I. Goodfellow, Y. Bengio, A. Courville, Deep Learning, MIT Press
        [authors' notes]

      • Additional material provided by the Teacher (after each lecture):
            [01-Intro]    [02-Data Regression]    [03-Bias_Variance]
            [04-Training_Schemes]    [05-Regularization]    [06-Clustering]      
            [07-Classification]    [08a-RBF_ELM]    [08b-Time_Series_ESN (ext)]
            [09-Quantum_Computing]    [10-DL_Intro]    [11-DeepRNN]
            [12-CNN]    [13-HDC_VSA (ext)]
        Note: the extended slides (ext) contain additional pages for illustrative purposes only; the supplementary slides (suppl) contain optional study material.
        Note: Python and Matlab notebooks used during the hands-on lectures were shared on Google Classroom to registered students who attended the course.

      • Other optional readings:

        • • T. Hastie, R. Tibshirani, J. Friedman, The Elements of Statistical Learning (2nd Ed.), Springer Series in Statistics

          • E. Alpaydin, Introduction to Machine Learning (3rd Ed.), MIT Press [author's notes]

          • C.M. Bishop, Pattern Recognition and Machine Learning, Springer

          • S. Theodoridis, Machine Learning: A Bayesian and Optimization Perspective, Academic Press

          • S.O. Haykin, Neural Networks and Learning Machines (3rd Ed.), Pearson

          • S. Theodoridis, K. Koutroumbas, Pattern Recognition (4th Ed.), Academic Press

          • B. Kosko, Neural Networks and Fuzzy Systems: A Dynamical Systems Approach to Machine Intelligence, Prentice-Hall

NOTICE. For each type of communication or inquiries related to the course, students are kindly requested to send me an e-mail writing in the SUBJECT "Machine Learning IE" and in the text body the following data: name, surname and university ID number. I will try to answer as soon as possible.